A Dynamic Anomaly Detection Approach Based on Permutation Entropy for Predicting Aging-Related Failures
Software aging is a phenomenon referring to the performance degradation of a long-running software system. This phenomenon is an accumulative process during execution, which will gradually lead the system from a normal state to a failure-prone state. It is a crucial challenge for system reliability...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/22/11/1225 |
| _version_ | 1797549671298629632 |
|---|---|
| author | Shuguang Wang Minyan Lu Shiyi Kong Jun Ai |
| author_facet | Shuguang Wang Minyan Lu Shiyi Kong Jun Ai |
| author_sort | Shuguang Wang |
| collection | DOAJ |
| description | Software aging is a phenomenon referring to the performance degradation of a long-running software system. This phenomenon is an accumulative process during execution, which will gradually lead the system from a normal state to a failure-prone state. It is a crucial challenge for system reliability to predict the Aging-Related Failures (ARFs) accurately. In this paper, permutation entropy (PE) is modified to Multidimensional Multi-scale Permutation Entropy (MMPE) as a novel aging indicator to detect performance anomalies, since MMPE is sensitive to dynamic state changes. An experiment is set on the distributed database system Voldemort, and MMPE is calculated based on the collected performance metrics during execution. Finally, based on MMPE, a failure prediction model using the machine learning method to reveal the anomalies is presented, which can predict failures with high accuracy. |
| first_indexed | 2024-03-10T15:17:47Z |
| format | Article |
| id | doaj.art-60eac5fdeda94ee695cf01bba7d1c9fd |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-10T15:17:47Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-60eac5fdeda94ee695cf01bba7d1c9fd2023-11-20T18:45:53ZengMDPI AGEntropy1099-43002020-10-012211122510.3390/e22111225A Dynamic Anomaly Detection Approach Based on Permutation Entropy for Predicting Aging-Related FailuresShuguang Wang0Minyan Lu1Shiyi Kong2Jun Ai3School of Reliability and Systems Engineering, Beihang University, Beijing 100089, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100089, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100089, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100089, ChinaSoftware aging is a phenomenon referring to the performance degradation of a long-running software system. This phenomenon is an accumulative process during execution, which will gradually lead the system from a normal state to a failure-prone state. It is a crucial challenge for system reliability to predict the Aging-Related Failures (ARFs) accurately. In this paper, permutation entropy (PE) is modified to Multidimensional Multi-scale Permutation Entropy (MMPE) as a novel aging indicator to detect performance anomalies, since MMPE is sensitive to dynamic state changes. An experiment is set on the distributed database system Voldemort, and MMPE is calculated based on the collected performance metrics during execution. Finally, based on MMPE, a failure prediction model using the machine learning method to reveal the anomalies is presented, which can predict failures with high accuracy.https://www.mdpi.com/1099-4300/22/11/1225software agingfailure predictionanomaly detectionmachine learning |
| spellingShingle | Shuguang Wang Minyan Lu Shiyi Kong Jun Ai A Dynamic Anomaly Detection Approach Based on Permutation Entropy for Predicting Aging-Related Failures Entropy software aging failure prediction anomaly detection machine learning |
| title | A Dynamic Anomaly Detection Approach Based on Permutation Entropy for Predicting Aging-Related Failures |
| title_full | A Dynamic Anomaly Detection Approach Based on Permutation Entropy for Predicting Aging-Related Failures |
| title_fullStr | A Dynamic Anomaly Detection Approach Based on Permutation Entropy for Predicting Aging-Related Failures |
| title_full_unstemmed | A Dynamic Anomaly Detection Approach Based on Permutation Entropy for Predicting Aging-Related Failures |
| title_short | A Dynamic Anomaly Detection Approach Based on Permutation Entropy for Predicting Aging-Related Failures |
| title_sort | dynamic anomaly detection approach based on permutation entropy for predicting aging related failures |
| topic | software aging failure prediction anomaly detection machine learning |
| url | https://www.mdpi.com/1099-4300/22/11/1225 |
| work_keys_str_mv | AT shuguangwang adynamicanomalydetectionapproachbasedonpermutationentropyforpredictingagingrelatedfailures AT minyanlu adynamicanomalydetectionapproachbasedonpermutationentropyforpredictingagingrelatedfailures AT shiyikong adynamicanomalydetectionapproachbasedonpermutationentropyforpredictingagingrelatedfailures AT junai adynamicanomalydetectionapproachbasedonpermutationentropyforpredictingagingrelatedfailures AT shuguangwang dynamicanomalydetectionapproachbasedonpermutationentropyforpredictingagingrelatedfailures AT minyanlu dynamicanomalydetectionapproachbasedonpermutationentropyforpredictingagingrelatedfailures AT shiyikong dynamicanomalydetectionapproachbasedonpermutationentropyforpredictingagingrelatedfailures AT junai dynamicanomalydetectionapproachbasedonpermutationentropyforpredictingagingrelatedfailures |